HOME   ::  Conference List   ::   Conference Paper
Gmytrasiewicz, P. J., Summers, M., and Gopal, D. (2002) Toward Automated Evolution of Agent Communication Languages. In Proceedings of the 35th Hawaii International Conference on System Sciences, HICSS-35.
Bookmark:  

Full-text
   URL: http://www.cs.uic.edu/~piotr/papers/hicss02-language.ps
   Cached: PDF-193K    PS-206K    PS.gz-75K   
   SAVE AS an easy-to-recall long filename:
      Filename format: author--year--title   PDF-193K    PS-75K    :: About GZip'd PS
      Filename format: author--year--title--journal|proceedings|...--pages   PDF-193K    PS-75K   

Related links
  Web search: Google Web Search   ::   Google Scholar
  Within this site: Cited by (2)    References (45)

Paper at a Glance 

Toward Automated Evolution of Agent Communication Languages
Piotr J. Gmytrasiewicz
Computer Science Department
University of Illinois, Chicago, IL 60607-7053
Matthew Summers and Dhruva Gopal
CSE Dept., University of Texas, Arlington, TX, 76019{0015
piotr@cs.uic.edu summers@dhc.net gopal@cse.uta.edu
Abstract The aim of our research is to understand and au- tomate the mechanisms by which language can emerge among arti cial, knowledge-based and ra- tional agents. We want to design and implement agents that, upon encountering other agent(s) with which they do not share an agent communication language, are able to initiate creation of, and fur- ther are able to evolve and enrich, a mutually understandable communication language. Our re- search is supported by the principled methodology of designing rational, socially competent arti cial agents based on Bayesian probability and decision theories, and on the research in linguistics and cog- nitive psychology that addresses the issues of func- tion, mechanisms, development, and evolutionary history of natural languages. In our work, we ex- press some of the key insights obtained in linguistics and cognitive science in formal terms of decision theory and game-theoretic mechanism design. We propose that the evolution of an agent communi- cation language can be accomplished by the mech- anism of negotiation, developed in economics and game theory, and automated in recent work in ar- ti cial intelligence. Negotiation is suitable because it can be mapped to settings in which rational in- teracting agents could use communication for their mutual, yet sel sh, bene ts. The agents can make mutually bene cial agreements that will allow ef- cient communication, but they have a conict of interest about which language constructs to use { each would prefer a communication language that is easier and less costly to use from their own indi- vidual perspective.
Introduction The aim of our research is to understand and au- tomate the ...
BibTex
@inproceedings{gmytrasiewicz02towardAutomated,
  author={Piotr J. Gmytrasiewicz and Matthew Summers and Dhruva Gopal},
  title={Toward Automated Evolution of Agent Communication Languages},
  year={2002},
  month={January},
  booktitle={Proceedings of the 35th Hawaii International Conference on System Sciences, HICSS-35},
  url={http://www.isrl.uiuc.edu/~amag/langev/paper/gmytrasiewicz02towardAutomated.html}
}

 HOME   ::  Conference List   ::   Conference Paper Comments to: junwang4 you-know-at gmail.com Last update: 2/2/08